FreshRouter
PricingDocs
Log inGet API key

Get started

  • Quick start

Tools

  • Claude Code
  • Codex
  • Pi
  • Grok Build
  • Cursor
  • Cline, Roo Code, Kilo Code
  • Open WebUI
  • LibreChat
  • Chatbox
  • n8n

Reference

  • SDKs
  • API reference
  • Prompt caching
  • Tool calling and images
  • Limits
  • Errors

Get started

  • Quick start

Tools

  • Claude Code
  • Codex
  • Pi
  • Grok Build
  • Cursor
  • Cline, Roo Code, Kilo Code
  • Open WebUI
  • LibreChat
  • Chatbox
  • n8n

Reference

  • SDKs
  • API reference
  • Prompt caching
  • Tool calling and images
  • Limits
  • Errors
FreshRouter

One key for every top AI model. Pay only for what you use.

Product

  • Pricing
  • Console

Resources

  • Quick start
  • Documentation

Legal

  • Terms of Service
  • Privacy Policy

© 2026 FreshRouter. All rights reserved.

Limits

How many requests an account can send, and how big they can be.

The limits count all of an account's keys together. They are the same for every account.

LimitValuePast it
Requests running at once50429, code too_many_running_requests
Requests running at once, balance under $25One per $0.5 of balance, at least 2429, code low_balance_running_limit
Requests started per minute300429
Requests answered per minute120429
Size of one request32 MB413, code request_too_large
Request data of all running requests64 MB429, code too_much_request_data
Compressed requests (Content-Encoding)Not accepted415

After a 429, wait a couple of seconds and try again: a slot frees as soon as a running request finishes. The official SDKs retry by themselves.

A request runs to its end even if you disconnect, streamed or not, and is billed in full. It keeps its slot until it has finished.

Errors from a model's provider

When a model's provider fails, the API answers 502 with the code provider_error, or 429 with provider_rate_limited when it is overloaded. Neither is charged. Try again shortly; the official SDKs do so by themselves.

Not supported

WebSocket connections answer 400 with the code websocket_not_supported: ask for a streamed answer over HTTP instead. GPT models take OpenAI's formats only (/v1/responses and /v1/chat/completions); in Gemini's format they answer 404.

Balance

A request is refused with 403 and the code insufficient_user_quota when the balance can't cover it; the message says where to top up. The cost of a request's input is set aside before it runs, so a nearly empty balance can refuse a large request while small ones still pass. When the balance runs low the console warns you, and you get an email, or a message from our bot if you signed in with Telegram.

Limits of your own

Each key can have a spending limit, a list of allowed models, allowed IP addresses and an expiry date: set them when you create the key in Console → API keys. The models and addresses can be changed later. A key that has used up its spending limit answers 403 with the code key_limit_reached.

PreviousTool calling and imagesNextErrors